Improvement in automated diagnosis of soft tissues tumors using machine learning

Alaoui, El Arbi Abdellaoui; Tékouabou, Stéphane Cédric Koumétio; Hartini, Sri; Rustam, Zuherman; Satori, Hassan; Agoujil, Saïd

doi:10.26599/bdma.2020.9020023

Cited by 30 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning algorithms like Support vector machines and Decision trees are used for the classification of the dataset. [11][12][13] Radiomics-based machine learning algorithm is also used for the detection of metastases from STS. A dataset consisting of 54 training sets and 23 validation test sets is used for this study.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of deep learning techniques for identification of sarcoma-causing carcinogenic mutations

et al. 2022

View full text Add to dashboard Cite

The abnormal growth of human healthy cells is called cancer. One of the major types of cancer is sarcoma, mostly found in human bones and soft tissue cells. It commonly occurs in children. According to a survey of the United States of America, there are more than 17,000 sarcoma patients registered each year which is 15% of all cancer cases. Recognition of cancer at its early stage saves many lives. The proposed study developed a framework for the early detection of human sarcoma cancer using deep learning Recurrent Neural Network (RNN) algorithms. The DNA of a human cell is made up of 25,000 to 30,000 genes. Each gene is represented by sequences of nucleotides. The nucleotides in a sequence of a driver gene can change which is termed as mutations. Some mutations can cause cancer. There are seven types of a gene whose mutation causes sarcoma cancer. The study uses the dataset which has been taken from more than 134 samples and includes 141 mutations in 8 driver genes. On these gene sequences RNN algorithms Long and Short-Term Memory (LSTM), Gated Recurrent Units and Bi-directional LSTM (Bi-LSTM) are used for training. Rigorous testing techniques such as Self-consistency testing, independent set testing, 10-fold cross-validation test are applied for the validation of results. These validation techniques yield several metrics such as Area Under the Curve (AUC), sensitivity, specificity, Mathew's correlation coefficient, loss, and accuracy. The proposed algorithm exhibits an accuracy of 99.6% with an AUC value of 1.00.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…Machine learning algorithms like Support vector machines and Decision trees are used for the classification of the dataset. 11 – 13 …”

Section: Introductionmentioning

confidence: 99%

Evaluation of deep learning techniques for identification of sarcoma-causing carcinogenic mutations

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In recent decades, several machine-learning methods have been applied in the context of soft tissue tumors (1)(2)(3). Soft tissue sarcomas (STSs) are highly heterogeneous tumors.…”

Section: Introductionmentioning

confidence: 99%

Radiomics model based on intravoxel incoherent motion and diffusion kurtosis imaging for predicting histopathological grade and Ki-67 expression level of soft tissue sarcomas

Zhu,

Li,

Zhang

et al. 2023

Acta Radiol

View full text Add to dashboard Cite

Background Accurate identification of the histopathological grade and the Ki-67 expression level is important in clinical cases of soft tissue sarcomas (STSs). Purpose To explore the feasibility of a radiomics model based on intravoxel incoherent motion (IVIM) magnetic resonance imaging (MRI) and diffusion kurtosis imaging (DKI) MRI parameter maps in predicting the histopathological grade and Ki-67 expression level of STSs. Material and Methods In total, 42 patients diagnosed with STSs between May 2018 and January 2020 were selected. The MADC software in Functool of GE ADW 4.7 workstation was used to obtain standard apparent diffusion coefficient (ADC), D, D*, f, mean diffusivity, and mean kurtosis (MK). The histopathological grade and Ki-67 expression level of STSs were identified. The radiomics features of IVIM and DKI parameter maps were used as the dataset. The area under the receiver operating characteristic curve (AUC) and F1-score were calculated. Results D-SVM achieved the best diagnostic performance for histopathological grade. The AUC in the validation cohort was 0.88 (sensitivity: 0.75 [low level] and 0.83 [high level]; specificity: 0.83 [low level] and 0.75 [high level]; F1-score: 0.75 [low level] and 0.83 [high level]). MK-SVM achieved the best diagnostic performance for Ki-67 expression level. The AUC in the validation cohort was 0.83 (sensitivity: 0.83 [low level] and 0.50 [high level; specificity: 0.50 [low level] and 0.83 [high level]; F1-score: 0.77 [low level] and 0.57 [high level]). Conclusion The proposed radiomics classifier could predict the pathological grade of STSs and the Ki-67 expression level in STSs.

show abstract

“…In recent years, deep learning methods have been widely used in computer vision [7] , and convolutional neural networks have made some progress in medical image processing. Alaoui et al [8] proposed a method based on machine learning to classify tumors. Shelhamer et al [9] used the fully convolutional neural network (FCNN) for the first time to perform pixel-level segmentation of natural images.…”

Section: Introductionmentioning

confidence: 99%

Combining residual attention mechanisms and generative adversarial networks for hippocampus segmentation

Deng

Zhang

et al. 2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

This research discussed a deep learning method based on an improved generative adversarial network to segment the hippocampus. Different convolutional configurations were proposed to capture information obtained by a segmentation network. In addition, a generative adversarial network based on Pixel2Pixel was proposed. The generator was a codec structure combining a residual network and an attention mechanism to capture detailed information. The discriminator used a convolutional neural network to discriminate the segmentation results of the generated model and that of the expert. Through the continuously transmitted losses of the generator and discriminator, the generator reached the optimal state of hippocampus segmentation. T1-weighted magnetic resonance imaging scans and related hippocampus labels of 130 healthy subjects from the Alzheimer's disease Neuroimaging Initiative dataset were used as training and test data; similarity coefficient, sensitivity, and positive predictive value were used as evaluation indicators. Results showed that the network model could achieve an efficient automatic segmentation of the hippocampus and thus has practical relevance for the correct diagnosis of diseases, such as Alzheimer's disease.

show abstract

Improvement in automated diagnosis of soft tissues tumors using machine learning

Cited by 30 publications

References 22 publications

Evaluation of deep learning techniques for identification of sarcoma-causing carcinogenic mutations

Evaluation of deep learning techniques for identification of sarcoma-causing carcinogenic mutations

Radiomics model based on intravoxel incoherent motion and diffusion kurtosis imaging for predicting histopathological grade and Ki-67 expression level of soft tissue sarcomas

Combining residual attention mechanisms and generative adversarial networks for hippocampus segmentation

Contact Info

Product

Resources

About